© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20924
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in programming or structured data formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.65
     nakalista
    -0.65
    +#+
    -0.62
    FunctionFlags
    -0.62
     strdup
    -0.57
    ściej
    -0.57
     loadImage
    -0.56
     hom
    -0.56
    nezeu
    -0.55
    ))->
    -0.54
    POSITIVE LOGITS
    KommentareTeilen
    0.56
    reactivex
    0.54
     AssemblyTitle
    0.54
     undone
    0.54
    Демографія
    0.54
    OGND
    0.52
    InSection
    0.52
    ウンテン
    0.52
     ujednoznacz
    0.51
     }{@
    0.51
    Activations Density 0.027%

    No Known Activations